Classification Training
Browse files
README.md
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: dslim/distilbert-NER
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
- f1
|
| 10 |
+
- precision
|
| 11 |
+
- recall
|
| 12 |
+
model-index:
|
| 13 |
+
- name: distilbert-classn-LinearAlg-finetuned-pred-span-width-5
|
| 14 |
+
results: []
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 18 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 19 |
+
|
| 20 |
+
# distilbert-classn-LinearAlg-finetuned-pred-span-width-5
|
| 21 |
+
|
| 22 |
+
This model is a fine-tuned version of [dslim/distilbert-NER](https://huggingface.co/dslim/distilbert-NER) on the None dataset.
|
| 23 |
+
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.6177
|
| 25 |
+
- Accuracy: 0.8492
|
| 26 |
+
- F1: 0.8483
|
| 27 |
+
- Precision: 0.8737
|
| 28 |
+
- Recall: 0.8492
|
| 29 |
+
|
| 30 |
+
## Model description
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Intended uses & limitations
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training and evaluation data
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Training procedure
|
| 43 |
+
|
| 44 |
+
### Training hyperparameters
|
| 45 |
+
|
| 46 |
+
The following hyperparameters were used during training:
|
| 47 |
+
- learning_rate: 1e-05
|
| 48 |
+
- train_batch_size: 2
|
| 49 |
+
- eval_batch_size: 2
|
| 50 |
+
- seed: 42
|
| 51 |
+
- gradient_accumulation_steps: 2
|
| 52 |
+
- total_train_batch_size: 4
|
| 53 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 54 |
+
- lr_scheduler_type: linear
|
| 55 |
+
- lr_scheduler_warmup_steps: 500
|
| 56 |
+
- num_epochs: 30
|
| 57 |
+
- mixed_precision_training: Native AMP
|
| 58 |
+
|
| 59 |
+
### Training results
|
| 60 |
+
|
| 61 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
| 62 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
| 63 |
+
| 5.1256 | 0.6849 | 50 | 2.4038 | 0.1270 | 0.0923 | 0.1177 | 0.1270 |
|
| 64 |
+
| 5.0918 | 1.3699 | 100 | 2.3642 | 0.1508 | 0.1164 | 0.1424 | 0.1508 |
|
| 65 |
+
| 4.9252 | 2.0548 | 150 | 2.3183 | 0.1905 | 0.1577 | 0.1813 | 0.1905 |
|
| 66 |
+
| 4.871 | 2.7397 | 200 | 2.2588 | 0.1984 | 0.1741 | 0.2039 | 0.1984 |
|
| 67 |
+
| 4.7135 | 3.4247 | 250 | 2.1740 | 0.3016 | 0.2812 | 0.3889 | 0.3016 |
|
| 68 |
+
| 4.4839 | 4.1096 | 300 | 2.0073 | 0.3810 | 0.3573 | 0.4049 | 0.3810 |
|
| 69 |
+
| 4.089 | 4.7945 | 350 | 1.8097 | 0.4762 | 0.4608 | 0.5123 | 0.4762 |
|
| 70 |
+
| 3.7117 | 5.4795 | 400 | 1.6202 | 0.5952 | 0.5875 | 0.6159 | 0.5952 |
|
| 71 |
+
| 3.0244 | 6.1644 | 450 | 1.4372 | 0.6508 | 0.6382 | 0.7022 | 0.6508 |
|
| 72 |
+
| 2.6119 | 6.8493 | 500 | 1.2138 | 0.6746 | 0.6621 | 0.6894 | 0.6746 |
|
| 73 |
+
| 2.0546 | 7.5342 | 550 | 1.0689 | 0.6984 | 0.6874 | 0.7277 | 0.6984 |
|
| 74 |
+
| 1.5176 | 8.2192 | 600 | 0.9357 | 0.7619 | 0.7650 | 0.8379 | 0.7619 |
|
| 75 |
+
| 1.1514 | 8.9041 | 650 | 0.8404 | 0.7937 | 0.7887 | 0.8468 | 0.7937 |
|
| 76 |
+
| 0.8779 | 9.5890 | 700 | 0.7515 | 0.7698 | 0.7674 | 0.7985 | 0.7698 |
|
| 77 |
+
| 0.5939 | 10.2740 | 750 | 0.6833 | 0.8016 | 0.8010 | 0.8354 | 0.8016 |
|
| 78 |
+
| 0.475 | 10.9589 | 800 | 0.6577 | 0.8175 | 0.8159 | 0.8515 | 0.8175 |
|
| 79 |
+
| 0.2866 | 11.6438 | 850 | 0.5898 | 0.8254 | 0.8239 | 0.8492 | 0.8254 |
|
| 80 |
+
| 0.2275 | 12.3288 | 900 | 0.5941 | 0.8413 | 0.8401 | 0.8636 | 0.8413 |
|
| 81 |
+
| 0.1275 | 13.0137 | 950 | 0.6122 | 0.8254 | 0.8285 | 0.8676 | 0.8254 |
|
| 82 |
+
| 0.1359 | 13.6986 | 1000 | 0.5818 | 0.8254 | 0.8233 | 0.8464 | 0.8254 |
|
| 83 |
+
| 0.0648 | 14.3836 | 1050 | 0.6180 | 0.8333 | 0.8326 | 0.8613 | 0.8333 |
|
| 84 |
+
| 0.0865 | 15.0685 | 1100 | 0.5762 | 0.8413 | 0.8392 | 0.8629 | 0.8413 |
|
| 85 |
+
| 0.0496 | 15.7534 | 1150 | 0.6235 | 0.8254 | 0.8223 | 0.8498 | 0.8254 |
|
| 86 |
+
| 0.0237 | 16.4384 | 1200 | 0.5911 | 0.8413 | 0.8389 | 0.8560 | 0.8413 |
|
| 87 |
+
| 0.0287 | 17.1233 | 1250 | 0.6150 | 0.8333 | 0.8319 | 0.8566 | 0.8333 |
|
| 88 |
+
| 0.0181 | 17.8082 | 1300 | 0.6299 | 0.8333 | 0.8324 | 0.8577 | 0.8333 |
|
| 89 |
+
| 0.0098 | 18.4932 | 1350 | 0.6181 | 0.8413 | 0.8399 | 0.8690 | 0.8413 |
|
| 90 |
+
| 0.0182 | 19.1781 | 1400 | 0.5949 | 0.8413 | 0.8408 | 0.8590 | 0.8413 |
|
| 91 |
+
| 0.0092 | 19.8630 | 1450 | 0.6146 | 0.8333 | 0.8324 | 0.8577 | 0.8333 |
|
| 92 |
+
| 0.0051 | 20.5479 | 1500 | 0.6092 | 0.8413 | 0.8412 | 0.8632 | 0.8413 |
|
| 93 |
+
| 0.0068 | 21.2329 | 1550 | 0.6137 | 0.8413 | 0.8412 | 0.8632 | 0.8413 |
|
| 94 |
+
| 0.0044 | 21.9178 | 1600 | 0.6238 | 0.8492 | 0.8483 | 0.8737 | 0.8492 |
|
| 95 |
+
| 0.0173 | 22.6027 | 1650 | 0.6199 | 0.8333 | 0.8324 | 0.8577 | 0.8333 |
|
| 96 |
+
| 0.0037 | 23.2877 | 1700 | 0.5989 | 0.8333 | 0.8324 | 0.8577 | 0.8333 |
|
| 97 |
+
| 0.0031 | 23.9726 | 1750 | 0.6229 | 0.8492 | 0.8483 | 0.8737 | 0.8492 |
|
| 98 |
+
| 0.0032 | 24.6575 | 1800 | 0.6169 | 0.8492 | 0.8483 | 0.8737 | 0.8492 |
|
| 99 |
+
| 0.0033 | 25.3425 | 1850 | 0.6022 | 0.8492 | 0.8483 | 0.8737 | 0.8492 |
|
| 100 |
+
| 0.0054 | 26.0274 | 1900 | 0.6097 | 0.8492 | 0.8483 | 0.8737 | 0.8492 |
|
| 101 |
+
| 0.0025 | 26.7123 | 1950 | 0.6182 | 0.8492 | 0.8483 | 0.8737 | 0.8492 |
|
| 102 |
+
| 0.0029 | 27.3973 | 2000 | 0.6222 | 0.8492 | 0.8483 | 0.8737 | 0.8492 |
|
| 103 |
+
| 0.0029 | 28.0822 | 2050 | 0.6148 | 0.8492 | 0.8483 | 0.8737 | 0.8492 |
|
| 104 |
+
| 0.0027 | 28.7671 | 2100 | 0.6134 | 0.8492 | 0.8483 | 0.8737 | 0.8492 |
|
| 105 |
+
| 0.0027 | 29.4521 | 2150 | 0.6177 | 0.8492 | 0.8483 | 0.8737 | 0.8492 |
|
| 106 |
+
|
| 107 |
+
|
| 108 |
+
### Framework versions
|
| 109 |
+
|
| 110 |
+
- Transformers 4.48.3
|
| 111 |
+
- Pytorch 2.5.1+cu124
|
| 112 |
+
- Datasets 3.3.0
|
| 113 |
+
- Tokenizers 0.21.0
|
runs/Feb17_12-47-47_7737c83a0c53/events.out.tfevents.1739796471.7737c83a0c53.3283.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52bc83651c3bacba983069aa9cdbba08131c72af1b87817c2adb229d1f477583
|
| 3 |
+
size 35361
|